Indeed AI’s future is not just bigger, it is more open-ended, agentic, and global than ever.
The revolution is here, and it’s just getting started.
#ICLR25 #AI #AGI #AIResearch #OpenEndedness #Robotics #SwarmAgents #ICLRConference #MachineLearning #DeepLearning #FutureOfAI #ICLRConference2025
Come hear Matt Smart's talk about in-context denoising with transformers at the Associative memory workshop #ICLR25, 2:15pm! This task refines the connection between transformers and associative memories. w/ M Smart and @albertobietti.bsky.social at @flatironinstitute.org
This afternoon Liza Tennant will present our paper "Moral Alignment for LLM Agents" at @iclr-conf.bsky.social 2025.
Time: 3pm Singapore time
Location: Hall 3 + Hall 2B #238
Paper: openreview.net/pdf?id=MeGDm...
Poster+video: iclr.cc/virtual/2025...
#ICLR2025 #ICLR25
Curious about fine-grained text-to-image model evaluation? Come see our spotlight paper on Gecko 🦎 in the afternoon poster session at #ICLR25
🏆Hall 3 + Hall 2B #359
🎖️Friday 3pm
ICLR: iclr.cc/virtual/2025...
Paper: arxiv.org/abs/2404.16820
Prompts: github.com/google-deepm...
Why do LLMs hallucinate with RAG?! 🤔
Find out at my #ICLR25 poster on Sufficient Context! 👋🏼
📍Hall 3 + Hall 2B #230
⏰ Fri 25 Apr 10 a.m. to 12:30 p.m.
Picture of a crowd listening to our awesome introduction of the session “towards tokenizer-free end to end architectures”
If you are at #ICLR25 and care about tokenizers, drop by Aleph Alpha’s Birds of a Feather session – happening now at Opal 103.
nice big boards for a poster session, well separated one from another, and with plenty of space to walk in between the poster rows 💙
well done, @iclr-conf.bsky.social #ICLR25!
(take notes @aaai.org.web.brid.gy !)
Image of the Singapore pavilion at the World Expo in Osaka.
From the Singapore Pavillon at #EXPO2025 to the real thing at #ICLR25!
Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
#ICLR25
openreview.net/forum?id=ReI...
NNs
✨better than fixed-feature (kernel, sieve) when target has low spatial homogeneity,
✨more sample-efficient wrt Stage 1
Kim, @dimitrimeunier.bsky.social, Suzuki, Li
Excited to be in Singapore 🇸🇬 for #ICLR25! We’ll present 1) Meta Motivo, a first-of-its-kind model enabling zero-shot humanoid control for any reward, goal, or motion; 2) imitation via successor feature matching; 3) flow matching for generative TD learning of future experience.
Headed to #ICLR25 next week! I'll...
▶️...have posters at the ML4RS, CCAI & MLMP workshops
▶️...give a talk at the ML4RS workshop on Apr 27 (ml-for-rs.github.io/iclr2025/)
▶️...am organizing the CCAI workshop on Apr 28 (climatechange.ai/events/iclr2...)
Wanna chat #GeoAI? Reach out!🎉
Headed to #ICLR25? Want to connect more with the AI x sustainability community? Check out our networking event, organized jointly with FCL (fcl.ethz.ch) and supported by @mila-quebec.bsky.social . 👇👇👇
Learn more about the event & register (for free) here: tinyurl.com/CCAIxFCL
I wanted to highlight that our project website (with code!) for our progressively-refined training with physics simulations is up now at: kanishkbh.github.io/prdp-paper/ #ICLR25 , the main ideas are: match network approximation and physics accuracy, refine the physics over the course of training.
Throwing compute at things has proven quite powerful in other domains but until recently not as much in #ReinforcementLearning.
Excited to share that out MAD-TD paper got a spotlight at #ICLR25! Check out Claas' thread on how to get the most out of your compute/data buck when training from scratch.
"Compositional Entailment Learning for Hyperbolic Vision-Language Models" #ICLR25
has been 𝐬𝐞𝐥𝐞𝐜𝐭𝐞𝐝 𝐟𝐨𝐫 𝐚𝐧 𝐨𝐫𝐚𝐥 𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 🏆
1.8% of the submitted papers were selected for an oral
"Following the Human Thread in Social Navigation" #ICLR25
has been 𝐬𝐞𝐥𝐞𝐜𝐭𝐞𝐝 𝐚𝐬 𝐬𝐩𝐨𝐭𝐥𝐢𝐠𝐡𝐭 🏅
5.1% of the submitted papers were selected for a spotlight or an oral
Check out our papers #iclr25 !
"Following the Human Thread in Social Navigation" #ICLR25
With: Luca Scofano, Alessio Sampieri, Tommaso Campari, Valentino Sacco, Indro Spinelli, @lambertoballan.bsky.social
Paper: arxiv.org/abs/2404.11327
"Compositional Entailment Learning for Hyperbolic Vision-Language Models" #ICLR25
With: Avik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno, Alessandro Flaborea, and @pascalmettes.bsky.social
Paper: arxiv.org/abs/2410.06912
Our @pinlab.bsky.social has 2 #ICLR25 papers accepted!
I'm proud of the strong team and of the fantastic collaborators.
Our EML team has 4 #ICLR25 Papers accepted! I am proud of my students and grateful to be a part of many successful collaborations. More details will appear on our website (www.eml-munich.de) but here are the snapshots.
Unpopular opinion: if #ICLR25 reviews weren't public I'd probably drop my papers without engaging in the discussion. Public reviews force me to respond to defend my papers, especially against synthetic, factually wrong critiques that would undermine my contributions
need to detox from #ICLR25 rebuttals.
now I am very allergic to reviewers not understanding probabilities and logical arguments 🤧
